© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 178014
    Prev
    Next
    INDEX
    Explanations

    Proof of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_29_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     हसीना
    0.40
     खासकर
    0.39
     returnMe
    0.39
     মাহমু
    0.38
    パネル
    0.38
    躹
    0.38
    மணி
    0.38
     चंद
    0.37
    बांग
    0.37
    <0x07>
    0.37
    POSITIVE LOGITS
    杜
    0.39
     virulence
    0.35
     harmless
    0.34
    ประกอบ
    0.34
     identificación
    0.33
     Höhen
    0.33
     unaffected
    0.32
    現
    0.32
     virulent
    0.32
     অনুপস্থিত
    0.32
    Activations Density 0.001%

    No Known Activations